Nemotron 3 Super 120B A12B

nvidia· 2026-03-11· 262K ctx

open weightsreasoning quant: unknown

spread (output)

10×

$0.250 – $2.50 · 12 providers

12 providers priced · 1 omitted (stale)

Provider	Input	Output	Cache rd	Blended
Kenari relay router	free/—	free/—	—	free/—
Requesty relay router	free/—	free/—	—	free/—
OpenRouter unknown	free/—	free/—	—	free/—
Kenari relay router	free/—	free/—	—	free/—
Kilo Gateway relay router	free/—	free/—	—	free/—
NanoGPT relay router	$0.050	$0.250	$0.025	$0.052
Eden AIstale relay router	$0.085	$0.400	—	$0.114^*
OpenRouter unknown	$0.080	$0.450	—	$0.114^*
Kilo Gateway relay router	$0.080	$0.450	—	$0.114^*
Pioneerfp8 relay router	$0.090	$0.450	$0.090	$0.130
Vercel AI Gateway unknown	$0.150	$0.650	—	$0.195^*
Nvidia relay router	$0.200	$0.800	—	$0.255^*
Nebius Token Factory relay router	$0.300	$0.900	—	$0.355^*
TensorX relay router	$0.300	$0.900	$0.075	$0.242
Eden AI relay router	$0.300	$0.900	$0.300	$0.355
Synthetic relay router	$0.300	$1.00	$0.300	$0.364
Crusoeoutlier relay router	$0.300	$2.40	$0.150	$0.396
Perplexity Agentoutlier unknown	$0.250	$2.50	—	$0.455^*

Cheapest (output)

NanoGPT

$0.250 /M

opencode.json

{
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "nvidia/nemotron-3-super-120b-a12b": {}
      }
    }
  }
}

Set NANO_GPT_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.